Hugging Face's logo

Shakhovak
/
Mistral-7B-Instruct-v0.2-absa-MT-laptops

Generated from Trainer
Model card Files Community
Shakhovak commited on
Commit
9168029
•
1 Parent(s): 5411110

End of training

Browse files
Files changed (3) hide show
  1. README.md +31 -31
  2. adapter_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0055
19
 
20
  ## Model description
21
 
@@ -50,36 +50,36 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.8622 | 0.13 | 40 | 0.1426 |
54
- | 0.0711 | 0.25 | 80 | 0.0191 |
55
- | 0.0159 | 0.38 | 120 | 0.0151 |
56
- | 0.0128 | 0.5 | 160 | 0.0145 |
57
- | 0.014 | 0.63 | 200 | 0.0119 |
58
- | 0.0116 | 0.75 | 240 | 0.0127 |
59
- | 0.0098 | 0.88 | 280 | 0.0097 |
60
- | 0.0096 | 1.0 | 320 | 0.0091 |
61
- | 0.008 | 1.13 | 360 | 0.0103 |
62
- | 0.0069 | 1.25 | 400 | 0.0091 |
63
- | 0.0075 | 1.38 | 440 | 0.0090 |
64
- | 0.0068 | 1.5 | 480 | 0.0080 |
65
- | 0.0058 | 1.63 | 520 | 0.0078 |
66
- | 0.0065 | 1.75 | 560 | 0.0076 |
67
- | 0.0058 | 1.88 | 600 | 0.0071 |
68
- | 0.0054 | 2.0 | 640 | 0.0066 |
69
- | 0.0034 | 2.13 | 680 | 0.0068 |
70
- | 0.0043 | 2.25 | 720 | 0.0070 |
71
- | 0.0033 | 2.38 | 760 | 0.0068 |
72
- | 0.0027 | 2.5 | 800 | 0.0066 |
73
- | 0.0028 | 2.63 | 840 | 0.0066 |
74
- | 0.0032 | 2.75 | 880 | 0.0059 |
75
- | 0.0029 | 2.88 | 920 | 0.0063 |
76
- | 0.0026 | 3.0 | 960 | 0.0055 |
77
- | 0.0015 | 3.13 | 1000 | 0.0056 |
78
- | 0.0013 | 3.26 | 1040 | 0.0058 |
79
- | 0.001 | 3.38 | 1080 | 0.0057 |
80
- | 0.0013 | 3.51 | 1120 | 0.0056 |
81
- | 0.0009 | 3.63 | 1160 | 0.0055 |
82
- | 0.0012 | 3.76 | 1200 | 0.0055 |
83
 
84
 
85
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0060
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 0.8786 | 0.13 | 40 | 0.1392 |
54
+ | 0.0627 | 0.25 | 80 | 0.0165 |
55
+ | 0.0162 | 0.38 | 120 | 0.0143 |
56
+ | 0.0139 | 0.5 | 160 | 0.0125 |
57
+ | 0.0131 | 0.63 | 200 | 0.0110 |
58
+ | 0.0115 | 0.75 | 240 | 0.0106 |
59
+ | 0.0111 | 0.88 | 280 | 0.0105 |
60
+ | 0.0091 | 1.0 | 320 | 0.0093 |
61
+ | 0.0073 | 1.13 | 360 | 0.0090 |
62
+ | 0.0079 | 1.25 | 400 | 0.0090 |
63
+ | 0.0068 | 1.38 | 440 | 0.0083 |
64
+ | 0.0065 | 1.5 | 480 | 0.0076 |
65
+ | 0.0071 | 1.63 | 520 | 0.0076 |
66
+ | 0.0062 | 1.75 | 560 | 0.0077 |
67
+ | 0.0062 | 1.88 | 600 | 0.0069 |
68
+ | 0.0058 | 2.0 | 640 | 0.0069 |
69
+ | 0.0034 | 2.13 | 680 | 0.0070 |
70
+ | 0.0034 | 2.25 | 720 | 0.0066 |
71
+ | 0.0034 | 2.38 | 760 | 0.0071 |
72
+ | 0.0038 | 2.5 | 800 | 0.0064 |
73
+ | 0.0032 | 2.63 | 840 | 0.0070 |
74
+ | 0.0031 | 2.75 | 880 | 0.0062 |
75
+ | 0.0032 | 2.88 | 920 | 0.0058 |
76
+ | 0.0026 | 3.0 | 960 | 0.0059 |
77
+ | 0.0018 | 3.13 | 1000 | 0.0058 |
78
+ | 0.0014 | 3.26 | 1040 | 0.0059 |
79
+ | 0.0014 | 3.38 | 1080 | 0.0060 |
80
+ | 0.0012 | 3.51 | 1120 | 0.0060 |
81
+ | 0.0014 | 3.63 | 1160 | 0.0060 |
82
+ | 0.001 | 3.76 | 1200 | 0.0060 |
83
 
84
 
85
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:428526abab4698328e33f0d39de6518a21c2230b5c5d7106b6fed07a5299062b
3
  size 218196746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5757fdb406d87c15a505a63c67c6805c16d48edd64e484e8336c079551de22aa
3
  size 218196746
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8514fb1e62310f7d88ee49617abf3f2a55840b0e6423eb0b1b5959f187555a8
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac45da7e2d2f6c7eb4def10d09d871c98f963ac7bb8ee6205c4a0d101579faf8
3
  size 4984